efficientnet_b0(pretrained: bool = False, overrides: object = {})EfficientNet-B0 feature-extracting backbone (compound coefficient ).
Builds an EfficientNet with the NAS-designed baseline
topology from Tan & Le, 2019 (Table 1): seven MBConv stages
with block repeats (1, 2, 2, 3, 3, 4, 1), channel
progression 16 → 24 → 40 → 80 → 112 → 192 → 320, and a
1×1 head expansion to 1280 channels. Approximately 5.3M
parameters and 77.1% ImageNet-1k top-1 accuracy at the
224×224 native resolution (Table 2).
Model Size
Parameters
pretrainedbool= FalseReserved for future pretrained-weight loading. Currently
ignored — the returned model is randomly initialised.
**overridesobject= {}Keyword overrides forwarded into
EfficientNetConfig.Returns
EfficientNetBackbone with the B0 configuration applied (or with
overrides merged on top of it).
Notes
See Tan & Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks", ICML 2019 (arXiv:1905.11946), Table 1 and Table 2.
Examples
>>> import lucid
>>> from lucid.models.vision.efficientnet import efficientnet_b0
>>> model = efficientnet_b0()
>>> x = lucid.randn(1, 3, 224, 224)
>>> out = model(x)
>>> out.last_hidden_state.shape
(1, 1280, 1, 1)